Content Based Image Recognition

Content based image retrieval is a difficult methodology of capturing relevant pictures from a large space for storing. Although this area has been explored for decades, no technique has achieved the accuracy of human visual perception in distinguishing pictures. We used a set of features vector by extracting totally different quite options that has its own significance like we tend to use texture options extracted by GLCM matrix that considers however usually a pixel with the intensity value i happens in a specific spatial  relationship to a pixel with the value j, Gabor filter, which is a powerful texture extraction technique either in describing the content of image regions or the global content of a picture. Color histogram as a global color feature and histogram intersection as color similarity metric. Except these statistical features and wavelet features are also utilized in combination of above features set. The content identification task is performed by the machine learning approaches. The machine learning algorithms provide better classification accuracy.  The optimality of global content is adopted via machine learning classifiers .